© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 9868
    Prev
    Next
    INDEX
    Explanations

    economic terms and conditions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    551
    +0.10
    0.5%
    230
    +0.10
    0.4%
    2
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.10
    0.08
    718
    +0.10
    0.07
    739
    +0.09
    0.03
    Negative Logits
     Memor
    -0.81
     learns
    -0.66
     Lis
    -0.65
     copying
    -0.63
    pheus
    -0.63
     ARC
    -0.63
     notation
    -0.61
     fishes
    -0.60
     node
    -0.59
     likes
    -0.59
    POSITIVE LOGITS
     overshadow
    1.19
     exacerbated
    1.18
     outweigh
    1.11
     dissu
    1.07
    acerb
    1.05
     detract
    1.05
     exacerbate
    1.03
     motivate
    1.03
     outwe
    1.03
     necess
    1.03
    Activations Density 0.672%

    No Known Activations